Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ExtractorHTML: Fix srcset by normalizing elementContext() to lowercase #478

Merged
merged 2 commits into from
Apr 27, 2022
Merged

ExtractorHTML: Fix srcset by normalizing elementContext() to lowercase #478

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
aac7441
ExtractorHTML: Fix srcset by normalizing elementContext() to lowercase
ato Apr 22, 2022
914756f
ExtractorHTML: Add a main() method to run the extractor standalone
ato Apr 22, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 29 additions & 1 deletion modules/src/main/java/org/archive/modules/extractor/ExtractorHTML.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,9 +20,12 @@
package org.archive.modules.extractor;

import java.io.IOException;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import java.net.URL;
import java.net.URLDecoder;
import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.Locale;
Expand All @@ -33,6 +36,7 @@

import com.google.common.base.Ascii;
import org.apache.commons.httpclient.URIException;
import org.apache.commons.io.IOUtils;
import org.archive.io.ReplayCharSequence;
import org.archive.modules.CoreAttributeConstants;
import org.archive.modules.CrawlMetadata;
Expand Down Expand Up @@ -1090,7 +1094,31 @@ protected void processStyle(CrawlURI curi, CharSequence sequence,
* @return CharSequence context
*/
public static CharSequence elementContext(CharSequence element, CharSequence attribute) {
return attribute == null? "": element + "/@" + attribute;
return attribute == null? "": (element + "/@" + attribute).toLowerCase(Locale.ROOT);
}

public static void main(String[] args) throws Exception {
if (args.length == 0 || args[0].equals("-h") || args[0].equals("--help")) {
System.err.println("Usage: ExtractorHTML URL");
System.err.println("Extracts and prints links from the given URL");
System.exit(1);
}

String url = args[0];
CrawlURI curi = new CrawlURI(UURIFactory.getInstance(url));

ExtractorHTML extractor = new ExtractorHTML();
extractor.setExtractorJS(new ExtractorJS());
extractor.afterPropertiesSet();

String content;
try (InputStream stream = new URL(url).openStream()) {
content = IOUtils.toString(stream, StandardCharsets.ISO_8859_1);
}
extractor.extract(curi, content);
for (CrawlURI link : curi.getOutLinks()) {
System.out.println(link.getURI() + " " + link.getLastHop() + " " + link.getViaContext());
}
}
}

8 changes: 5 additions & 3 deletions modules/src/test/java/org/archive/modules/extractor/ExtractorHTMLTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -545,8 +545,8 @@ public void testSourceSrcSetAttribute() throws URIException {

CharSequence cs = "<picture>"
+ "<source media=\"(min-width: 992px)\" srcset=\"images/foo1.jpg\"> "
+ "<source media=\"(min-width: 500px)\" srcset=\"images/foo2.jpg\"> "
+ "<source media=\"(min-width: 0px)\" srcset=\"images/foo3.jpg\"> "
+ "<source media=\"(min-width: 500px)\" SRCSET=\"images/foo2.jpg\"> "
+ "<source media=\"(min-width: 0px)\" srcSet=\"images/foo3-1x.jpg 1x, images/foo3-2x.jpg 2x\"> "
+ "<img src=\"images/foo.jpg\" alt=\"\"> "
+ "</picture>";

Expand All @@ -559,7 +559,9 @@ public void testSourceSrcSetAttribute() throws URIException {
"http://www.example.com/images/foo.jpg",
"http://www.example.com/images/foo1.jpg",
"http://www.example.com/images/foo2.jpg",
"http://www.example.com/images/foo3.jpg" };
"http://www.example.com/images/foo3-1x.jpg",
"http://www.example.com/images/foo3-2x.jpg",
};

for (int i = 0; i < links.length; i++) {
assertEquals("outlink from picture", dest[i], links[i].getURI());
Expand Down